Longitudinal Study-Based Dementia Prediction for Public Health

Dementia and the history of disease in older adults in community

INTRODUCTION

Many studies have revealed the effect of medical history on dementia. The aim of this study was to explore the relationship between the history of disease and onset of dementia.

METHODS

This was a multi-center, cross-sectional study, with 2595 older adults enrolled. The onset of dementia was evaluated with Revised Hasegawa Dementia Scale (HDS-R). The diagnosed diseases after the age of 40 of the participants were investigated, including respiratory system diseases, digestive system diseases, cardiovascular diseases, endocrine disorders, genitourinary system diseases, nervous system disease, sensory system diseases, dental/oral diseases, bone/joint diseases and mental illnesses.

RESULTS

Data of 2458 older adults were analyzed. Univariate analysis showed that diabetes, thyroid disease, mental illness, hearing loss, stroke, dental/oral disease, Denture use, fracture/osteoporosis, kidney disease and number of diseases were risk factors for dementia. After controlling for demographic sociological variables, diabetes, dental/oral disease, and denture use were independent risk factors for dementia. Thyroid disease (P = 0.313), mental illnesses (P = 0.067), hearing loss (P = 0.595), stroke (P = 0.538), fractures/osteoporosis (P = 0.069), kidney disease (P = 0.168) were no longer significant to dementia.

CONCLUSION

Diabetes, dental/oral disease and denture use were main risk factors for dementia.

Cognitive decline sensitivity by educational level and residential area: A descriptive study using long-term care insurance dementia registration data in South Korea

In South Korea Long-Term Care Insurance (LTCI) system, the special dementia rating (SDR) is a registration grading for dementia patients who do not have a physical disability or functional restrictions and is the first applicable registration following the diagnosis of dementia. We investigated the differences in age of registration of SDR and age of dementia diagnosis according to the educational level and residential area. This was a retrospective, cross-sectional study using the Korean National Health Insurance Service dataset. Applications for SDR between July 2014 and December 2016 were identified for participant selection, and 32,352 patients with dementia were included. Educational levels were defined as follows: the illiterate, only-reading, 1 to 6 years, 6 to 12 years, and ≥12 years. Urban residents were those who lived in the city, as ascertained from the Korean administrative district system. The primary outcomes were ages at the time of dementia diagnosis and SDR registration. A lower education level significantly correlated with a higher proportion of older adults, but a higher number of years of education significantly increased with the proportion of males and urban residents (P < .001 for all). A higher education level was inversely associated with the age at diagnosis of dementia (P < .001) and at the registration of SDR (P < .001). Urban residents were diagnosed with dementia at a significantly lower age and registered for SDR earlier than rural residents (P < .001 for both). Both urban and rural residents consistently showed that a higher educational level was associated with lower age at the dementia diagnosis and SDR registration. Patients who were highly educated and living in urban areas were diagnosed with dementia and registered on SDR when they were relatively younger, indicating that cognitive decline sensitivity and medical accessibility are related to earlier dementia diagnosis and registration.

One-year prediction of cognitive decline following cognitive-stimulation from real-world data

Clinical evidence based on real-world data (RWD) is accumulating exponentially providing larger sample sizes available, which demand novel methods to deal with the enhanced heterogeneity of the data. Here, we used RWD to assess the prediction of cognitive decline in a large heterogeneous sample of participants being enrolled with cognitive stimulation, a phenomenon that is of great interest to clinicians but that is riddled with difficulties and limitations. More precisely, from a multitude of neuropsychological Training Materials (TMs), we asked whether was possible to accurately predict an individual's cognitive decline one year after being tested. In particular, we performed longitudinal modelling of the scores obtained from 215 different tests, grouped into 29 cognitive domains, a total of 124,610 instances from 7902 participants (40% male, 46% female, 14% not indicated), each performing an average of 16 tests. Employing a machine learning approach based on ROC analysis and cross-validation techniques to overcome overfitting, we show that different TMs belonging to several cognitive domains can accurately predict cognitive decline, while other domains perform poorly, suggesting that the ability to predict decline one year later is not specific to any particular domain, but is rather widely distributed across domains. Moreover, when addressing the same problem between individuals with a common diagnosed label, we found that some domains had more accurate classification for conditions such as Parkinson's disease and Down syndrome, whereas they are less accurate for Alzheimer's disease or multiple sclerosis. Future research should combine similar approaches to ours with standard neuropsychological measurements to enhance interpretability and the possibility of generalizing across different cohorts.

The Role of Big Data in Aging and Older People’s Health Research: A Systematic Review and Ecological Framework

Big data has been prominent in studying aging and older people’s health. It has promoted modeling and analyses in biological and geriatric research (like cellular senescence), developed health management platforms, and supported decision-making in public healthcare and social security. However, current studies are still limited within a single subject, rather than flourished as interdisciplinary research in the context of big data. The research perspectives have not changed, nor has big data brought itself out of the role as a modeling tool. When embedding big data as a data product, analysis tool, and resolution service into different spatial, temporal, and organizational scales of aging processes, it would present as a connection, integration, and interaction simultaneously in conducting interdisciplinary research. Therefore, this paper attempts to propose an ecological framework for big data based on aging and older people’s health research. Following the scoping process of PRISMA, 35 studies were reviewed to validate our ecological framework. Although restricted by issues like digital divides and privacy security, we encourage researchers to capture various elements and their interactions in the human-environment system from a macro and dynamic perspective rather than simply pursuing accuracy.

Use of Machine Learning and Artificial Intelligence Methods in Geriatric Mental Health Research Involving Electronic Health Record or Administrative Claims Data: A Systematic Review

Introduction: Electronic health records (EHR) and administrative healthcare data (AHD) are frequently used in geriatric mental health research to answer various health research questions. However, there is an increasing amount and complexity of data available that may lend itself to alternative analytic approaches using machine learning (ML) or artificial intelligence (AI) methods. We performed a systematic review of the current application of ML or AI approaches to the analysis of EHR and AHD in geriatric mental health. Methods: We searched MEDLINE, Embase, and PsycINFO to identify potential studies. We included all articles that used ML or AI methods on topics related to geriatric mental health utilizing EHR or AHD data. We assessed study quality either by Prediction model Risk OF Bias ASsessment Tool (PROBAST) or Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) checklist. Results: We initially identified 391 articles through an electronic database and reference search, and 21 articles met inclusion criteria. Among the selected studies, EHR was the most used data type, and the datasets were mainly structured. A variety of ML and AI methods were used, with prediction or classification being the main application of ML or AI with the random forest as the most common ML technique. Dementia was the most common mental health condition observed. The relative advantages of ML or AI techniques compared to biostatistical methods were generally not assessed. Only in three studies, low risk of bias (ROB) was observed according to all the PROBAST domains but in none according to QUADAS-2 domains. The quality of study reporting could be further improved. Conclusion: There are currently relatively few studies using ML and AI in geriatric mental health research using EHR and AHD methods, although this field is expanding. Aside from dementia, there are few studies of other geriatric mental health conditions. The lack of consistent information in the selected studies precludes precise comparisons between them. Improving the quality of reporting of ML and AI work in the future would help improve research in the field. Other courses of improvement include using common data models to collect/organize data, and common datasets for ML model validation.

Medical Health Records-Based Mild Cognitive Impairment (MCI) Prediction for Effective Dementia Care

Dementia is a cognitive impairment that poses a global threat. Current dementia treatments slow the progression of the disease. The timing of starting such treatment markedly affects the effectiveness of the treatment. Some experts mentioned that the optimal timing for starting the currently available treatment in order to delay progression to dementia is the mild cognitive impairment stage, which is the prior stage of dementia. However, medical records are typically only available at a later stage, i.e., from the early or middle stage of dementia. In order to address this limitation, this study developed a model using national health information data from 5 years prior, to predict dementia development 5 years in the future. The Senior Cohort Database, comprising 550,000 samples, were used for model development. The F-measure of the model predicting dementia development after a 5-year incubation period was 77.38%. Models for a 1- and 3-year incubation period were also developed for comparative analysis of dementia risk factors. The three models had some risk factors in common, but also had unique risk factors, depending on the stage. For the common risk factors, a difference in disease severity was confirmed. These findings indicate that the diagnostic criteria and treatment strategy for dementia should differ depending on the timing. Furthermore, since the results of this study present new dementia risk factors that have not been reported previously, this study may also contribute to identification of new dementia risk factors.

Machine learning for modeling the progression of Alzheimer disease dementia using clinical data: a systematic literature review

OBJECTIVE

Alzheimer disease (AD) is the most common cause of dementia, a syndrome characterized by cognitive impairment severe enough to interfere with activities of daily life. We aimed to conduct a systematic literature review (SLR) of studies that applied machine learning (ML) methods to clinical data derived from electronic health records in order to model risk for progression of AD dementia.

MATERIALS AND METHODS

We searched for articles published between January 1, 2010, and May 31, 2020, in PubMed, Scopus, ScienceDirect, IEEE Explore Digital Library, Association for Computing Machinery Digital Library, and arXiv. We used predefined criteria to select relevant articles and summarized them according to key components of ML analysis such as data characteristics, computational algorithms, and research focus.

RESULTS

There has been a considerable rise over the past 5 years in the number of research papers using ML-based analysis for AD dementia modeling. We reviewed 64 relevant articles in our SLR. The results suggest that majority of existing research has focused on predicting progression of AD dementia using publicly available datasets containing both neuroimaging and clinical data (neurobehavioral status exam scores, patient demographics, neuroimaging data, and laboratory test values).

DISCUSSION

Identifying individuals at risk for progression of AD dementia could potentially help to personalize disease management to plan future care. Clinical data consisting of both structured data tables and clinical notes can be effectively used in ML-based approaches to model risk for AD dementia progression. Data sharing and reproducibility of results can enhance the impact, adaptation, and generalizability of this research.

Prevalence and Incidence of Dementia in South Korea: A Nationwide Analysis of the National Health Insurance Service Senior Cohort

BACKGROUND AND PURPOSE

Dementia is rapidly becoming more common in the elderly population of South Korea, and there are regional difference in its demographics. This study investigated the trajectories in the prevalence and incidence of dementia based on the Seoul metropolitan area and other areas in South Korea using big data from the National Health Insurance Service (NHIS).

METHODS

We examined a population-based elderly cohort obtained from the NHIS Senior Cohort (NHIS-SC) data set that comprises approximately half a million recipients of medical insurance in South Korea during 2003-2015. The age-standardized prevalence and incidence of dementia as well as their trajectories from 2003 were estimated. Regional differences in these rates between Seoul metropolitan area and other areas were also analyzed.

RESULTS

The standardized prevalence of dementia per 100,000 increased significantly from 178.11 in 2003 to 5,319.01 in 2015 (p<0.001). The standardized prevalence of dementia was higher in other areas than in Seoul metropolitan area. The standardized incidence of dementia per 100,000 person-years also increased significantly, from 126.41 in 2003 to 2,218.25 in 2015 (p<0.001). The standardized incidence of dementia was similarly higher in other areas than in Seoul metropolitan area (p<0.001).

CONCLUSIONS

This study has shown that the standardized prevalence and incidence of dementia increased steadily from 2003 to 2015 in South Korea based on the NHIS-SC data set, and differed between Seoul metropolitan area and other areas.

Alzheimer-type dementia prediction by sparse logistic regression using claim data

This study aimed to predict the risk of Alzheimer-type dementia for persons aged over 75 years old without receiving long-term care services using regularly collected claim data. A refined dataset including 48,123 persons was prepared from claim data of health insurance and long-term care insurance in a large city in the metropolitan area in Japan. The utilized features include the age and sex of subjects, 502 diseases based on ICD-10 diagnosis codes, and 107 prescription drugs based on therapeutic classes. The most important challenge in this work was feature selection form a large number of features. We adopted sparse logistic regression models with L0 regularization (SLR-L0) and L1 regularization (SLR-L1) as classification models based on machine learning. These regularizations enable feature selection by estimating sparse solution of non-zero coefficients in the model optimization. Predictions were performed by integrating 100 predictors trained by bootstrap samples. As a result, the area under the ROC curves (AUCs) were 0.663 for SLR-L0 and 0.660 for SLR-L1. These performances were similar, however, the average numbers of selected features were 13 out of a total of 611 for SLR-L0 and 253 for SLR-R1. The results indicate that SLR-L1 tended to include less useful features, whereas SLR-L0 narrowed down influential features. SLR-L0 might be more useful than SLR-L1 for practical use or the discussion of risk factors with medical experts.

Gender-Based Analysis of Risk Factors for Dementia Using Senior Cohort

Globally, one of the biggest problems with the increase in the elderly population is dementia. However, dementia still has no fundamental cure. Therefore, it is important to predict and prevent dementia early. For early prediction of dementia, it is crucial to find dementia risk factors that increase a person's risk of developing dementia. In this paper, the subject of dementia risk factor analysis and discovery studies were limited to gender, because it is assumed that the difference in the prevalence of dementia in men and women will lead to differences in the risk factors for dementia among men and women. This study analyzed the Korean National Health Information System-Senior Cohort using machine-learning techniques. By using the machine-learning technique, it was possible to reveal a very small causal relationship between data that are ignored using existing statistical techniques. By using the senior cohort, it was possible to analyze 6000 data that matched the experimental conditions out of 558,147 sample subjects over 14 years. In order to analyze the difference in dementia risk factors between men and women, three machine-learning-based dementia risk factor analysis models were constructed and compared. As a result of the experiment, it was found that the risk factors for dementia in men and women are different. In addition, not only did the results include most of the known dementia risk factors, previously unknown candidates for dementia risk factors were also identified. We hope that our research will be helpful in finding new dementia risk factors.

Dose response relationship of cumulative anticholinergic exposure with incident dementia: validation study of Korean anticholinergic burden scale

Background

The dose response relationship of nine-year cumulative anticholinergic exposure and dementia onset was investigated using the Korean version anticholinergic burden scale (KABS) in comparison with the Anticholinergic Cognitive Burden Scale (ACB). We also examined the effect of weak anticholinergics in the prediction of dementia.

Methods

A retrospective case-control study was conducted comprising 86,576 patients after 1:2 propensity score matching using the longitudinal national claims database. For cumulative anticholinergic burden estimation, average daily anticholinergic burden score during the 9 years prior to dementia onset was calculated using KABS and ACB and categorized as minimal, < 0.25; low, 0.25–1; intermediate, 1–2; and high, ≥ 2. Adjusted odds ratio (aOR) between cumulative anticholinergic burden and incident dementia was estimated.

Results

Patients with high exposure according to KABS and ACB comprised 3.2 and 3.4% of the dementia cohort and 2.1 and 2.8% of the non-dementia cohort, respectively. Dose-response relationships were observed between anticholinergic burden and incident dementia. After adjusting covariates, compared with minimal exposure, patients with high exposure according to KABS and ACB had a significantly higher risk for incident dementia with aOR of 1.71 (95% confidence interval (CI) 1.55–1.87) and 1.22 (CI 1.12–1.33), respectively. With the exclusion of weak anticholinergics, the association became stronger, i.e., 1.41 (CI 1.14–1.75) with ACB whereas the association became slightly weaker with KABS, i.e., 1.60 (CI 1.38–1.86).

Conclusion

This study confirmed the dose response relationship for cumulative anticholinergic burden measured using the Korean specific anticholinergic burden scale with incident dementia.

Cohort Profile: National health insurance service-senior (NHIS-senior) cohort in Korea

PURPOSE

The National Health Insurance Service (NHIS)-Senior was set up to provide high-quality longitudinal data that can be used to explore various aspects of changes in the socio-economical and health status of older adults, to predict risk factors and to investigate their health outcomes.

PARTICIPANTS

The NHIS-Senior cohort, a Korean nationwide retrospective administrative data cohort, is composed of older adults aged 60 years and over in 2002. It consists of 558 147 people selected by 10% simple random sampling method from a total of 5.5 million subjects aged 60+ in the National Health Information Database. The cohort was followed up through 2015 for all subjects, except for those who were deceased.

FINDINGS TO DATE

The healthcare utilisation and admission rates were the highest for acute upper respiratory infections and influenza (75.2%). The age-standardised (defined with reference to the world standard population) mortality rate for 10 years (through 2012) was 4333 per 100 000 person-years. Malignant neoplasms were the most common cause of death in both sexes (1032.1 per 100 000 person-years for men, 376.7 per 100 000 person-years for women). A total of 34 483 individuals applied for long-term care service in 2008, of whom 17.9% were assessed as grade 1, meaning that they were completely dependent on the help of another person to live daily life.

FUTURE PLANS

The data are provided for the purposes of policy and academic research under the Act on Promotion of the Provision and Use of Public Data in Korea. The NHIS-Senior cohort data are only available for Korean researchers at the moment, but it is possible for researchers outside the country to gain access to the data by conducting a joint study with a Korean researcher. The cohort will be maintained and continuously updated by the NHIS.

Machine learning in mental health: a scoping review of methods and applications

BACKGROUND

This paper aims to synthesise the literature on machine learning (ML) and big data applications for mental health, highlighting current research and applications in practice.

METHODS

We employed a scoping review methodology to rapidly map the field of ML in mental health. Eight health and information technology research databases were searched for papers covering this domain. Articles were assessed by two reviewers, and data were extracted on the article's mental health application, ML technique, data type, and study results. Articles were then synthesised via narrative review.

RESULTS

Three hundred papers focusing on the application of ML to mental health were identified. Four main application domains emerged in the literature, including: (i) detection and diagnosis; (ii) prognosis, treatment and support; (iii) public health, and; (iv) research and clinical administration. The most common mental health conditions addressed included depression, schizophrenia, and Alzheimer's disease. ML techniques used included support vector machines, decision trees, neural networks, latent Dirichlet allocation, and clustering.

CONCLUSIONS

Overall, the application of ML to mental health has demonstrated a range of benefits across the areas of diagnosis, treatment and support, research, and clinical administration. With the majority of studies identified focusing on the detection and diagnosis of mental health conditions, it is evident that there is significant room for the application of ML to other areas of psychology and mental health. The challenges of using ML techniques are discussed, as well as opportunities to improve and advance the field.

Wave2Vec: Vectorizing Electroencephalography Bio-Signal for Prediction of Brain Disease

Interest in research involving health-medical information analysis based on artificial intelligence, especially for deep learning techniques, has recently been increasing. Most of the research in this field has been focused on searching for new knowledge for predicting and diagnosing disease by revealing the relation between disease and various information features of data. These features are extracted by analyzing various clinical pathology data, such as EHR (electronic health records), and academic literature using the techniques of data analysis, natural language processing, etc. However, still needed are more research and interest in applying the latest advanced artificial intelligence-based data analysis technique to bio-signal data, which are continuous physiological records, such as EEG (electroencephalography) and ECG (electrocardiogram). Unlike the other types of data, applying deep learning to bio-signal data, which is in the form of time series of real numbers, has many issues that need to be resolved in preprocessing, learning, and analysis. Such issues include leaving feature selection, learning parts that are black boxes, difficulties in recognizing and identifying effective features, high computational complexities, etc. In this paper, to solve these issues, we provide an encoding-based Wave2vec time series classifier model, which combines signal-processing and deep learning-based natural language processing techniques. To demonstrate its advantages, we provide the results of three experiments conducted with EEG data of the University of California Irvine, which are a real-world benchmark bio-signal dataset. After converting the bio-signals (in the form of waves), which are a real number time series, into a sequence of symbols or a sequence of wavelet patterns that are converted into symbols, through encoding, the proposed model vectorizes the symbols by learning the sequence using deep learning-based natural language processing. The models of each class can be constructed through learning from the vectorized wavelet patterns and training data. The implemented models can be used for prediction and diagnosis of diseases by classifying the new data. The proposed method enhanced data readability and intuition of feature selection and learning processes by converting the time series of real number data into sequences of symbols. In addition, it facilitates intuitive and easy recognition, and identification of influential patterns. Furthermore, real-time large-capacity data analysis is facilitated, which is essential in the development of real-time analysis diagnosis systems, by drastically reducing the complexity of calculation without deterioration of analysis performance by data simplification through the encoding process.